/* allocate a r1bio with room for raid_disks entries in the bios array */
r1_bio = kzalloc(size, gfp_flags);
- if (!r1_bio)
+ if (!r1_bio && pi->mddev)
unplug_slaves(pi->mddev);
return r1_bio;
static void free_r1bio(r1bio_t *r1_bio)
{
- conf_t *conf = mddev_to_conf(r1_bio->mddev);
+ conf_t *conf = r1_bio->mddev->private;
/*
* Wake up any possible resync thread that waits for the device
static void put_buf(r1bio_t *r1_bio)
{
- conf_t *conf = mddev_to_conf(r1_bio->mddev);
+ conf_t *conf = r1_bio->mddev->private;
int i;
for (i=0; i<conf->raid_disks; i++) {
{
unsigned long flags;
mddev_t *mddev = r1_bio->mddev;
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
spin_lock_irqsave(&conf->device_lock, flags);
list_add(&r1_bio->retry_list, &conf->retry_list);
*/
static inline void update_head_pos(int disk, r1bio_t *r1_bio)
{
- conf_t *conf = mddev_to_conf(r1_bio->mddev);
+ conf_t *conf = r1_bio->mddev->private;
conf->mirrors[disk].head_position =
r1_bio->sector + (r1_bio->sectors);
static void raid1_end_read_request(struct bio *bio, int error)
{
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
+ r1bio_t *r1_bio = bio->bi_private;
int mirror;
- conf_t *conf = mddev_to_conf(r1_bio->mddev);
+ conf_t *conf = r1_bio->mddev->private;
mirror = r1_bio->read_disk;
/*
static void raid1_end_write_request(struct bio *bio, int error)
{
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
+ r1bio_t *r1_bio = bio->bi_private;
int mirror, behind = test_bit(R1BIO_BehindIO, &r1_bio->state);
- conf_t *conf = mddev_to_conf(r1_bio->mddev);
+ conf_t *conf = r1_bio->mddev->private;
struct bio *to_put = NULL;
static void unplug_slaves(mddev_t *mddev)
{
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
int i;
rcu_read_lock();
static int raid1_congested(void *data, int bits)
{
mddev_t *mddev = data;
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
int i, ret = 0;
+ if (mddev_congested(mddev, bits))
+ return 1;
+
rcu_read_lock();
for (i = 0; i < mddev->raid_disks; i++) {
mdk_rdev_t *rdev = rcu_dereference(conf->mirrors[i].rdev);
static void lower_barrier(conf_t *conf)
{
unsigned long flags;
+ BUG_ON(conf->barrier <= 0);
spin_lock_irqsave(&conf->resync_lock, flags);
conf->barrier--;
spin_unlock_irqrestore(&conf->resync_lock, flags);
static int make_request(struct request_queue *q, struct bio * bio)
{
mddev_t *mddev = q->queuedata;
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
mirror_info_t *mirror;
r1bio_t *r1_bio;
struct bio *read_bio;
struct bio_list bl;
struct page **behind_pages = NULL;
const int rw = bio_data_dir(bio);
- const int do_sync = bio_sync(bio);
- int cpu, do_barriers;
+ const bool do_sync = bio_rw_flagged(bio, BIO_RW_SYNCIO);
+ int cpu;
+ bool do_barriers;
mdk_rdev_t *blocked_rdev;
/*
md_write_start(mddev, bio); /* wait on superblock update early */
- if (unlikely(!mddev->barriers_work && bio_barrier(bio))) {
+ if (bio_data_dir(bio) == WRITE &&
+ bio->bi_sector + bio->bi_size/512 > mddev->suspend_lo &&
+ bio->bi_sector < mddev->suspend_hi) {
+ /* As the suspend_* range is controlled by
+ * userspace, we want an interruptible
+ * wait.
+ */
+ DEFINE_WAIT(w);
+ for (;;) {
+ flush_signals(current);
+ prepare_to_wait(&conf->wait_barrier,
+ &w, TASK_INTERRUPTIBLE);
+ if (bio->bi_sector + bio->bi_size/512 <= mddev->suspend_lo ||
+ bio->bi_sector >= mddev->suspend_hi)
+ break;
+ schedule();
+ }
+ finish_wait(&conf->wait_barrier, &w);
+ }
+ if (unlikely(!mddev->barriers_work &&
+ bio_rw_flagged(bio, BIO_RW_BARRIER))) {
if (rw == WRITE)
md_write_end(mddev);
bio_endio(bio, -EOPNOTSUPP);
read_bio->bi_sector = r1_bio->sector + mirror->rdev->data_offset;
read_bio->bi_bdev = mirror->rdev->bdev;
read_bio->bi_end_io = raid1_end_read_request;
- read_bio->bi_rw = READ | do_sync;
+ read_bio->bi_rw = READ | (do_sync << BIO_RW_SYNCIO);
read_bio->bi_private = r1_bio;
generic_make_request(read_bio);
if (test_bit(Faulty, &rdev->flags)) {
rdev_dec_pending(rdev, mddev);
r1_bio->bios[i] = NULL;
- } else
+ } else {
r1_bio->bios[i] = bio;
- targets++;
+ targets++;
+ }
} else
r1_bio->bios[i] = NULL;
}
/* do behind I/O ? */
if (bitmap &&
- atomic_read(&bitmap->behind_writes) < bitmap->max_write_behind &&
+ (atomic_read(&bitmap->behind_writes)
+ < mddev->bitmap_info.max_write_behind) &&
(behind_pages = alloc_behind_pages(bio)) != NULL)
set_bit(R1BIO_BehindIO, &r1_bio->state);
atomic_set(&r1_bio->remaining, 0);
atomic_set(&r1_bio->behind_remaining, 0);
- do_barriers = bio_barrier(bio);
+ do_barriers = bio_rw_flagged(bio, BIO_RW_BARRIER);
if (do_barriers)
set_bit(R1BIO_Barrier, &r1_bio->state);
mbio->bi_sector = r1_bio->sector + conf->mirrors[i].rdev->data_offset;
mbio->bi_bdev = conf->mirrors[i].rdev->bdev;
mbio->bi_end_io = raid1_end_write_request;
- mbio->bi_rw = WRITE | do_barriers | do_sync;
+ mbio->bi_rw = WRITE | (do_barriers << BIO_RW_BARRIER) |
+ (do_sync << BIO_RW_SYNCIO);
mbio->bi_private = r1_bio;
if (behind_pages) {
static void status(struct seq_file *seq, mddev_t *mddev)
{
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
int i;
seq_printf(seq, " [%d/%d] [", conf->raid_disks,
static void error(mddev_t *mddev, mdk_rdev_t *rdev)
{
char b[BDEVNAME_SIZE];
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
/*
* If it is not operational, then we have already marked it as dead
for (mirror = first; mirror <= last; mirror++)
if ( !(p=conf->mirrors+mirror)->rdev) {
- blk_queue_stack_limits(mddev->queue,
- rdev->bdev->bd_disk->queue);
- /* as we don't honour merge_bvec_fn, we must never risk
- * violating it, so limit ->max_sector to one PAGE, as
- * a one page request is never in violation.
+ disk_stack_limits(mddev->gendisk, rdev->bdev,
+ rdev->data_offset << 9);
+ /* as we don't honour merge_bvec_fn, we must
+ * never risk violating it, so limit
+ * ->max_segments to one lying with a single
+ * page, as a one page request is never in
+ * violation.
*/
- if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
- queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
- blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
+ if (rdev->bdev->bd_disk->queue->merge_bvec_fn) {
+ blk_queue_max_segments(mddev->queue, 1);
+ blk_queue_segment_boundary(mddev->queue,
+ PAGE_CACHE_SIZE - 1);
+ }
p->head_position = 0;
rdev->raid_disk = mirror;
rcu_assign_pointer(p->rdev, rdev);
break;
}
-
+ md_integrity_add_rdev(rdev, mddev);
print_conf(conf);
return err;
}
/* lost the race, try later */
err = -EBUSY;
p->rdev = rdev;
+ goto abort;
}
+ md_integrity_register(mddev);
}
abort:
static void end_sync_read(struct bio *bio, int error)
{
- r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
+ r1bio_t *r1_bio = bio->bi_private;
int i;
for (i=r1_bio->mddev->raid_disks; i--; )
static void end_sync_write(struct bio *bio, int error)
{
int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags);
- r1bio_t * r1_bio = (r1bio_t *)(bio->bi_private);
+ r1bio_t *r1_bio = bio->bi_private;
mddev_t *mddev = r1_bio->mddev;
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
int i;
int mirror=0;
static void sync_request_write(mddev_t *mddev, r1bio_t *r1_bio)
{
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
int i;
int disks = conf->raid_disks;
struct bio *bio, *wbio;
r1bio_t *r1_bio;
struct bio *bio;
unsigned long flags;
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
struct list_head *head = &conf->retry_list;
int unplug=0;
mdk_rdev_t *rdev;
spin_unlock_irqrestore(&conf->device_lock, flags);
mddev = r1_bio->mddev;
- conf = mddev_to_conf(mddev);
+ conf = mddev->private;
if (test_bit(R1BIO_IsSync, &r1_bio->state)) {
sync_request_write(mddev, r1_bio);
unplug = 1;
* We already have a nr_pending reference on these rdevs.
*/
int i;
- const int do_sync = bio_sync(r1_bio->master_bio);
+ const bool do_sync = bio_rw_flagged(r1_bio->master_bio, BIO_RW_SYNCIO);
clear_bit(R1BIO_BarrierRetry, &r1_bio->state);
clear_bit(R1BIO_Barrier, &r1_bio->state);
for (i=0; i < conf->raid_disks; i++)
conf->mirrors[i].rdev->data_offset;
bio->bi_bdev = conf->mirrors[i].rdev->bdev;
bio->bi_end_io = raid1_end_write_request;
- bio->bi_rw = WRITE | do_sync;
+ bio->bi_rw = WRITE |
+ (do_sync << BIO_RW_SYNCIO);
bio->bi_private = r1_bio;
r1_bio->bios[i] = bio;
generic_make_request(bio);
r1_bio->sector,
r1_bio->sectors);
unfreeze_array(conf);
- }
+ } else
+ md_error(mddev,
+ conf->mirrors[r1_bio->read_disk].rdev);
bio = r1_bio->bios[r1_bio->read_disk];
- if ((disk=read_balance(conf, r1_bio)) == -1 ||
- disk == r1_bio->read_disk) {
+ if ((disk=read_balance(conf, r1_bio)) == -1) {
printk(KERN_ALERT "raid1: %s: unrecoverable I/O"
" read error for block %llu\n",
bdevname(bio->bi_bdev,b),
(unsigned long long)r1_bio->sector);
raid_end_bio_io(r1_bio);
} else {
- const int do_sync = bio_sync(r1_bio->master_bio);
+ const bool do_sync = bio_rw_flagged(r1_bio->master_bio, BIO_RW_SYNCIO);
r1_bio->bios[r1_bio->read_disk] =
mddev->ro ? IO_BLOCKED : NULL;
r1_bio->read_disk = disk;
bio->bi_sector = r1_bio->sector + rdev->data_offset;
bio->bi_bdev = rdev->bdev;
bio->bi_end_io = raid1_end_read_request;
- bio->bi_rw = READ | do_sync;
+ bio->bi_rw = READ | (do_sync << BIO_RW_SYNCIO);
bio->bi_private = r1_bio;
unplug = 1;
generic_make_request(bio);
}
}
+ cond_resched();
}
if (unplug)
unplug_slaves(mddev);
static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster)
{
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
r1bio_t *r1_bio;
struct bio *bio;
sector_t max_sector, nr_sectors;
return mddev->dev_sectors;
}
-static int run(mddev_t *mddev)
+static conf_t *setup_conf(mddev_t *mddev)
{
conf_t *conf;
- int i, j, disk_idx;
+ int i;
mirror_info_t *disk;
mdk_rdev_t *rdev;
+ int err = -ENOMEM;
- if (mddev->level != 1) {
- printk("raid1: %s: raid level not set to mirroring (%d)\n",
- mdname(mddev), mddev->level);
- goto out;
- }
- if (mddev->reshape_position != MaxSector) {
- printk("raid1: %s: reshape_position set but not supported\n",
- mdname(mddev));
- goto out;
- }
- /*
- * copy the already verified devices into our private RAID1
- * bookkeeping area. [whatever we allocate in run(),
- * should be freed in stop()]
- */
conf = kzalloc(sizeof(conf_t), GFP_KERNEL);
- mddev->private = conf;
if (!conf)
- goto out_no_mem;
+ goto abort;
conf->mirrors = kzalloc(sizeof(struct mirror_info)*mddev->raid_disks,
GFP_KERNEL);
if (!conf->mirrors)
- goto out_no_mem;
+ goto abort;
conf->tmppage = alloc_page(GFP_KERNEL);
if (!conf->tmppage)
- goto out_no_mem;
+ goto abort;
- conf->poolinfo = kmalloc(sizeof(*conf->poolinfo), GFP_KERNEL);
+ conf->poolinfo = kzalloc(sizeof(*conf->poolinfo), GFP_KERNEL);
if (!conf->poolinfo)
- goto out_no_mem;
- conf->poolinfo->mddev = mddev;
+ goto abort;
conf->poolinfo->raid_disks = mddev->raid_disks;
conf->r1bio_pool = mempool_create(NR_RAID1_BIOS, r1bio_pool_alloc,
r1bio_pool_free,
conf->poolinfo);
if (!conf->r1bio_pool)
- goto out_no_mem;
+ goto abort;
- spin_lock_init(&conf->device_lock);
- mddev->queue->queue_lock = &conf->device_lock;
+ conf->poolinfo->mddev = mddev;
+ spin_lock_init(&conf->device_lock);
list_for_each_entry(rdev, &mddev->disks, same_set) {
- disk_idx = rdev->raid_disk;
+ int disk_idx = rdev->raid_disk;
if (disk_idx >= mddev->raid_disks
|| disk_idx < 0)
continue;
disk->rdev = rdev;
- blk_queue_stack_limits(mddev->queue,
- rdev->bdev->bd_disk->queue);
- /* as we don't honour merge_bvec_fn, we must never risk
- * violating it, so limit ->max_sector to one PAGE, as
- * a one page request is never in violation.
- */
- if (rdev->bdev->bd_disk->queue->merge_bvec_fn &&
- queue_max_sectors(mddev->queue) > (PAGE_SIZE>>9))
- blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
-
disk->head_position = 0;
}
conf->raid_disks = mddev->raid_disks;
bio_list_init(&conf->pending_bio_list);
bio_list_init(&conf->flushing_bio_list);
-
- mddev->degraded = 0;
+ conf->last_used = -1;
for (i = 0; i < conf->raid_disks; i++) {
disk = conf->mirrors + i;
if (!disk->rdev ||
!test_bit(In_sync, &disk->rdev->flags)) {
disk->head_position = 0;
- mddev->degraded++;
if (disk->rdev)
conf->fullsync = 1;
- }
+ } else if (conf->last_used < 0)
+ /*
+ * The first working device is used as a
+ * starting point to read balancing.
+ */
+ conf->last_used = i;
}
- if (mddev->degraded == conf->raid_disks) {
+
+ err = -EIO;
+ if (conf->last_used < 0) {
printk(KERN_ERR "raid1: no operational mirrors for %s\n",
- mdname(mddev));
- goto out_free_conf;
+ mdname(mddev));
+ goto abort;
}
- if (conf->raid_disks - mddev->degraded == 1)
- mddev->recovery_cp = MaxSector;
+ err = -ENOMEM;
+ conf->thread = md_register_thread(raid1d, mddev, NULL);
+ if (!conf->thread) {
+ printk(KERN_ERR
+ "raid1: couldn't allocate thread for %s\n",
+ mdname(mddev));
+ goto abort;
+ }
+
+ return conf;
+ abort:
+ if (conf) {
+ if (conf->r1bio_pool)
+ mempool_destroy(conf->r1bio_pool);
+ kfree(conf->mirrors);
+ safe_put_page(conf->tmppage);
+ kfree(conf->poolinfo);
+ kfree(conf);
+ }
+ return ERR_PTR(err);
+}
+
+static int run(mddev_t *mddev)
+{
+ conf_t *conf;
+ int i;
+ mdk_rdev_t *rdev;
+
+ if (mddev->level != 1) {
+ printk("raid1: %s: raid level not set to mirroring (%d)\n",
+ mdname(mddev), mddev->level);
+ return -EIO;
+ }
+ if (mddev->reshape_position != MaxSector) {
+ printk("raid1: %s: reshape_position set but not supported\n",
+ mdname(mddev));
+ return -EIO;
+ }
/*
- * find the first working one and use it as a starting point
- * to read balancing.
+ * copy the already verified devices into our private RAID1
+ * bookkeeping area. [whatever we allocate in run(),
+ * should be freed in stop()]
*/
- for (j = 0; j < conf->raid_disks &&
- (!conf->mirrors[j].rdev ||
- !test_bit(In_sync, &conf->mirrors[j].rdev->flags)) ; j++)
- /* nothing */;
- conf->last_used = j;
+ if (mddev->private == NULL)
+ conf = setup_conf(mddev);
+ else
+ conf = mddev->private;
+ if (IS_ERR(conf))
+ return PTR_ERR(conf);
- mddev->thread = md_register_thread(raid1d, mddev, "%s_raid1");
- if (!mddev->thread) {
- printk(KERN_ERR
- "raid1: couldn't allocate thread for %s\n",
- mdname(mddev));
- goto out_free_conf;
+ mddev->queue->queue_lock = &conf->device_lock;
+ list_for_each_entry(rdev, &mddev->disks, same_set) {
+ disk_stack_limits(mddev->gendisk, rdev->bdev,
+ rdev->data_offset << 9);
+ /* as we don't honour merge_bvec_fn, we must never risk
+ * violating it, so limit ->max_segments to 1 lying within
+ * a single page, as a one page request is never in violation.
+ */
+ if (rdev->bdev->bd_disk->queue->merge_bvec_fn) {
+ blk_queue_max_segments(mddev->queue, 1);
+ blk_queue_segment_boundary(mddev->queue,
+ PAGE_CACHE_SIZE - 1);
+ }
}
+ mddev->degraded = 0;
+ for (i=0; i < conf->raid_disks; i++)
+ if (conf->mirrors[i].rdev == NULL ||
+ !test_bit(In_sync, &conf->mirrors[i].rdev->flags) ||
+ test_bit(Faulty, &conf->mirrors[i].rdev->flags))
+ mddev->degraded++;
+
+ if (conf->raid_disks - mddev->degraded == 1)
+ mddev->recovery_cp = MaxSector;
+
+ if (mddev->recovery_cp != MaxSector)
+ printk(KERN_NOTICE "raid1: %s is not clean"
+ " -- starting background reconstruction\n",
+ mdname(mddev));
printk(KERN_INFO
"raid1: raid set %s active with %d out of %d mirrors\n",
mdname(mddev), mddev->raid_disks - mddev->degraded,
mddev->raid_disks);
+
/*
* Ok, everything is just fine now
*/
+ mddev->thread = conf->thread;
+ conf->thread = NULL;
+ mddev->private = conf;
+
md_set_array_sectors(mddev, raid1_size(mddev, 0, 0));
mddev->queue->unplug_fn = raid1_unplug;
mddev->queue->backing_dev_info.congested_fn = raid1_congested;
mddev->queue->backing_dev_info.congested_data = mddev;
-
+ md_integrity_register(mddev);
return 0;
-
-out_no_mem:
- printk(KERN_ERR "raid1: couldn't allocate memory for %s\n",
- mdname(mddev));
-
-out_free_conf:
- if (conf) {
- if (conf->r1bio_pool)
- mempool_destroy(conf->r1bio_pool);
- kfree(conf->mirrors);
- safe_put_page(conf->tmppage);
- kfree(conf->poolinfo);
- kfree(conf);
- mddev->private = NULL;
- }
-out:
- return -EIO;
}
static int stop(mddev_t *mddev)
{
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
struct bitmap *bitmap = mddev->bitmap;
int behind_wait = 0;
return -EINVAL;
set_capacity(mddev->gendisk, mddev->array_sectors);
mddev->changed = 1;
+ revalidate_disk(mddev->gendisk);
if (sectors > mddev->dev_sectors &&
mddev->recovery_cp == MaxSector) {
mddev->recovery_cp = mddev->dev_sectors;
mempool_t *newpool, *oldpool;
struct pool_info *newpoolinfo;
mirror_info_t *newmirrors;
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
int cnt, raid_disks;
unsigned long flags;
int d, d2, err;
/* Cannot change chunk_size, layout, or level */
- if (mddev->chunk_size != mddev->new_chunk ||
+ if (mddev->chunk_sectors != mddev->new_chunk_sectors ||
mddev->layout != mddev->new_layout ||
mddev->level != mddev->new_level) {
- mddev->new_chunk = mddev->chunk_size;
+ mddev->new_chunk_sectors = mddev->chunk_sectors;
mddev->new_layout = mddev->layout;
mddev->new_level = mddev->level;
return -EINVAL;
static void raid1_quiesce(mddev_t *mddev, int state)
{
- conf_t *conf = mddev_to_conf(mddev);
+ conf_t *conf = mddev->private;
switch(state) {
+ case 2: /* wake for suspend */
+ wake_up(&conf->wait_barrier);
+ break;
case 1:
raise_barrier(conf);
break;
}
}
+static void *raid1_takeover(mddev_t *mddev)
+{
+ /* raid1 can take over:
+ * raid5 with 2 devices, any layout or chunk size
+ */
+ if (mddev->level == 5 && mddev->raid_disks == 2) {
+ conf_t *conf;
+ mddev->new_level = 1;
+ mddev->new_layout = 0;
+ mddev->new_chunk_sectors = 0;
+ conf = setup_conf(mddev);
+ if (!IS_ERR(conf))
+ conf->barrier = 1;
+ return conf;
+ }
+ return ERR_PTR(-EINVAL);
+}
static struct mdk_personality raid1_personality =
{
.size = raid1_size,
.check_reshape = raid1_reshape,
.quiesce = raid1_quiesce,
+ .takeover = raid1_takeover,
};
static int __init raid_init(void)
module_init(raid_init);
module_exit(raid_exit);
MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("RAID1 (mirroring) personality for MD");
MODULE_ALIAS("md-personality-3"); /* RAID1 */
MODULE_ALIAS("md-raid1");
MODULE_ALIAS("md-level-1");
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff